On Committee Representations of Adversarial Learning Models for Question-Answer Ranking
Autor: | Sparsh Gupta, Vitor R. Carvalho |
---|---|
Rok vydání: | 2019 |
Předmět: |
Computer science
Process (engineering) business.industry 05 social sciences 010501 environmental sciences Overfitting Machine learning computer.software_genre 01 natural sciences Adversarial system Ranking 0502 economics and business Benchmark (computing) Learning to rank Artificial intelligence 050207 economics Baseline (configuration management) business Representation (mathematics) computer 0105 earth and related environmental sciences |
Zdroj: | RepL4NLP@ACL |
DOI: | 10.18653/v1/w19-4325 |
Popis: | Adversarial training is a process in Machine Learning that explicitly trains models on adversarial inputs (inputs designed to deceive or trick the learning process) in order to make it more robust or accurate. In this paper we investigate how representing adversarial training models as committees can be used to effectively improve the performance of Question-Answer (QA) Ranking. We start by empirically probing the effects of adversarial training over multiple QA ranking algorithms, including the state-of-the-art Multihop Attention Network model. We evaluate these algorithms on several benchmark datasets and observe that, while adversarial training is beneficial to most baseline algorithms, there are cases where it may lead to overfitting and performance degradation. We investigate the causes of such degradation, and then propose a new representation procedure for this adversarial learning problem, based on committee learning, that not only is capable of consistently improving all baseline algorithms, but also outperforms the previous state-of-the-art algorithm by as much as 6% in NDCG. |
Databáze: | OpenAIRE |
Externí odkaz: |